Comparison of classification methods for tissue outcome after ischaemic stroke.

Autor: Tozlu C; Université de Lyon, Lyon, France.; Université Lyon 1, Villeurbanne, France.; Hospices Civils de Lyon, Service de Biostatistique-Bioinformatique, Lyon, France.; CNRS, UMR5558, Laboratoire de Biométrie et de Biologie Évolutive, Équipe Biostatistique-Santé, Villeurbanne, France., Ozenne B; Neurobiology Research Unit, Rigshospitalet, Copenhagen O, Denmark.; Department of Public Health, Section of Biostatistics, University of Copenhagen, Copenhagen K, Denmark., Cho TH; Department of Stroke Medicine and Department of Neuroradiology, Université Lyon 1, CREATIS, CNRS, UMR 5220-INSERM U1044, INSA-Lyon, Hospices Civils de Lyon, Lyon, France., Nighoghossian N; Department of Stroke Medicine and Department of Neuroradiology, Université Lyon 1, CREATIS, CNRS, UMR 5220-INSERM U1044, INSA-Lyon, Hospices Civils de Lyon, Lyon, France., Mikkelsen IK; Center of Functionally Integrative Neuroscience, Aarhus University, Aarhus, Denmark., Derex L; Department of Stroke Medicine and Department of Neuroradiology, Université Lyon 1, CREATIS, CNRS, UMR 5220-INSERM U1044, INSA-Lyon, Hospices Civils de Lyon, Lyon, France., Hermier M; Department of Stroke Medicine and Department of Neuroradiology, Université Lyon 1, CREATIS, CNRS, UMR 5220-INSERM U1044, INSA-Lyon, Hospices Civils de Lyon, Lyon, France., Pedraza S; Department of Radiology (IDI), Girona Biomedical Research Institute (IDIBGI), Hospital Universitari de Girona Doctor Josep Trueta, Girona, Spain., Fiehler J; Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany., Østergaard L; Center of Functionally Integrative Neuroscience, Aarhus University, Aarhus, Denmark.; Department of Neuroradiology, Aarhus University Hospital, Aarhus, Denmark., Berthezène Y; Department of Stroke Medicine and Department of Neuroradiology, Université Lyon 1, CREATIS, CNRS, UMR 5220-INSERM U1044, INSA-Lyon, Hospices Civils de Lyon, Lyon, France.; Center of Functionally Integrative Neuroscience, Aarhus University, Aarhus, Denmark., Baron JC; Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK.; INSERM U894, Hôpital Sainte-Anne, Université Paris Descartes, Sorbonne Paris Cité, Paris, France., Maucort-Boulch D; Université de Lyon, Lyon, France.; Université Lyon 1, Villeurbanne, France.; Hospices Civils de Lyon, Service de Biostatistique-Bioinformatique, Lyon, France.; CNRS, UMR5558, Laboratoire de Biométrie et de Biologie Évolutive, Équipe Biostatistique-Santé, Villeurbanne, France.
Jazyk: angličtina
Zdroj: The European journal of neuroscience [Eur J Neurosci] 2019 Nov; Vol. 50 (10), pp. 3590-3598. Date of Electronic Publication: 2019 Sep 12.
DOI: 10.1111/ejn.14507
Abstrakt: In acute ischaemic stroke, identifying brain tissue at high risk of infarction is important for clinical decision-making. This tissue may be identified with suitable classification methods from magnetic resonance imaging data. The aim of the present study was to assess and compare the performance of five popular classification methods (adaptive boosting, logistic regression, artificial neural networks, random forest and support vector machine) in identifying tissue at high risk of infarction on human voxel-based brain imaging data. The classification methods were used with eight MRI parameters, including diffusion-weighted imaging and perfusion-weighted imaging obtained in 55 patients. The five criteria used to assess the performance of the methods were the area under the receiver operating curve (AUC roc ), the area under the precision-recall curve (AUC pr ), sensitivity, specificity and the Dice coefficient. The methods performed equally in terms of sensitivity and specificity, while the results of AUC roc and the Dice coefficient were significantly better for adaptive boosting, logistic regression, artificial neural networks and random forest. However, there was no statistically significant difference between the performances of these five classification methods regarding AUC pr , which was the main comparison metric. Machine learning methods can provide valuable prognostic information using multimodal imaging data in acute ischaemic stroke, which in turn can assist in developing personalized treatment decision for clinicians after a thorough validation of methods with an independent data set.
(© 2019 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje